Computer-implemented method for generating a response sentence by using a weight value of node

Abstract

A semantic network storage unit stores multiple nodes necessary for performing a task of generating a response sentence to user's speech while associating the nodes with each other. A natural language processor acquires speech information indicating content of the user's speech and identifies a primary node corresponding to the speech information from multiple nodes. A conversation generation unit selects one secondary node from multiple secondary nodes associated with the identified primary node, based on weight values each related to one of the multiple secondary nodes and generates a response sentence corresponding to the selected one secondary node.

What is claimed is: 
     
       1. A computer implemented speech recognition method for responding to user's speech comprising:
 acquiring, by a processor, speech information indicating content of user's speech; 
 identifying, by the processor, a primary node corresponding to the speech information from multiple nodes which are stored in a memory, the multiple nodes being necessary for performing a task of generating a response sentence to the user's speech while associating the multiple nodes with each other; 
 determining, by the processor, whether each of weight values each related to multiple secondary nodes associated with the identified primary node is larger than a predetermined value or not; 
 when a weight value related to one secondary node is determined to be larger than the predetermined value,
 selecting the one secondary node from the multiple secondary nodes, 
 generating the response sentence which asks to a user whether a content corresponding to the selected one secondary node is needed or not, and 
 outputting the response sentence to the user using a speaker; 
 
 when each of weight values related to two or more secondary nodes is determined to be larger than the predetermined value,
 selecting the two or more secondary nodes from the multiple secondary nodes, 
 generating the response sentence which asks to the user to select one of multiple contents, each of the multiple contents corresponding to each of the two or more secondary nodes, and 
 outputting the response sentence to the user using the speaker; and 
 
 when each of the weight values is determined not to be larger than the predetermined value,
 generating the response sentence which asks to the user what is needed related to the identified primary node, and 
 outputting the response sentence to the user using the speaker. 
 
 
     
     
       2. The computer implemented method according to  claim 1 , wherein
 information indicating an answer of the user to the response sentence is acquired, and 
 the weight values are updated depending on whether or not the user's answer is an answer to select one secondary node from the multiple secondary nodes. 
 
     
     
       3. The computer implemented method according to  claim 1 , wherein
 a weight value is related to a combination of a first secondary node of multiple secondary nodes associated with a first primary node of multiple primary nodes and each of multiple secondary nodes associated with a second primary node of the multiple primary nodes, 
 the processor determines whether the first secondary node is identified, and 
 in a case that the first secondary node is identified, a second secondary node is selected from the multiple secondary nodes associated with the second primary node, based on the weight values related to respective combinations of the first secondary node and the multiple secondary nodes associated with the second primary node. 
 
     
     
       4. A non-transitory medium having thereon a program for causing a processor to execute operations included in the method of  claim 1 . 
     
     
       5. The computer implemented method according to  claim 1 ,
 wherein each of the weight values is updated in each session. 
 
     
     
       6. A speech recognition apparatus for responding to user's speech comprising:
 a processor; and 
 a memory having thereon a program, the program causing the processor to execute operations including: 
 acquiring speech information indicating content of user's speech; 
 identifying a primary node corresponding to the speech information from multiple nodes which are stored in a recording medium, the multiple nodes being necessary for performing a task of generating a response sentence to the user's speech while associating the multiple nodes with each other; 
 determining whether each of weight values each related to multiple secondary nodes associated with the identified primary node is larger than a predetermined value or not; 
 when a weight value related to one secondary node is determined to be larger than the predetermined value,
 selecting the one secondary node from the multiple secondary nodes, 
 generating the response sentence which asks to a user whether a content corresponding to the selected one secondary node is needed or not, and 
 outputting the response sentence to the user using a speaker; 
 
 when each of weight values related to two or more secondary nodes is determined to be larger than the predetermined value,
 selecting the two or more secondary nodes from the multiple secondary nodes, 
 generating the response sentence which asks to the user to select one of multiple contents, each of the multiple contents corresponding to each of the two or more secondary nodes, and 
 outputting the response sentence to the user using the speaker; and 
 
 when each of the weight values is determined not to be larger than the predetermined value,
 generating the response sentence which asks to the user what is needed related to the identified primary node, and 
 outputting the response sentence to the user using the speaker.